© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30233
    Prev
    Next
    INDEX
    Explanations

    extremism

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on words and phrases related to terrorism, violent extremism, and counterterrorism.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jorg
    -0.78
    falt
    -0.77
     colonie
    -0.77
     Noida
    -0.74
    OME
    -0.74
     akrab
    -0.74
    NOC
    -0.73
     jupe
    -0.72
    eror
    -0.71
     Hound
    -0.71
    POSITIVE LOGITS
     extremism
    1.81
     Extre
    1.46
     counter
    1.40
     extremist
    1.32
     Counter
    1.30
     radical
    1.24
     extremists
    1.23
    counter
    1.22
     Prevent
    1.21
    CVE
    1.18
    Activations Density 0.020%

    No Known Activations